{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JAUYE53JHJSJLGIUGBSNH2JXCF","short_pith_number":"pith:JAUYE53J","schema_version":"1.0","canonical_sha256":"48298277693a649599143064d3e937115650aeacb6480989c20838ffac3a1b09","source":{"kind":"arxiv","id":"2203.10790","version":2},"attestation_state":"computed","paper":{"title":"ScalableViT: Rethinking the Context-oriented Generalization of Vision Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hailong Ma, Jie Wu, Min Zheng, Rui Yang, Xiu Li, Xuefeng Xiao, Yansong Tang","submitted_at":"2022-03-21T08:08:15Z","abstract_excerpt":"The vanilla self-attention mechanism inherently relies on pre-defined and steadfast computational dimensions. Such inflexibility restricts it from possessing context-oriented generalization that can bring more contextual cues and global representations. To mitigate this issue, we propose a Scalable Self-Attention (SSA) mechanism that leverages two scaling factors to release dimensions of query, key, and value matrices while unbinding them with the input. This scalability fetches context-oriented generalization and enhances object sensitivity, which pushes the whole network into a more effectiv"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2203.10790","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-21T08:08:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"074184bba5a2db6430d35c5cf66ed429ec8a512d11be2e34994621476a7d065e","abstract_canon_sha256":"fe7c29b268d0906eb446c7a09ebe0f2d2137d475bb569d078a8538bc8ae7302b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:40:52.605684Z","signature_b64":"/Tz4i4d0ZMhVZ7Z/TGiCVQuYyTTRjdPWZTwMM+zdRdlHNgQP85ocRLCUqKsue7qpRqrKr/l8kEWmSiimXhMGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48298277693a649599143064d3e937115650aeacb6480989c20838ffac3a1b09","last_reissued_at":"2026-07-05T04:40:52.605194Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:40:52.605194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ScalableViT: Rethinking the Context-oriented Generalization of Vision Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hailong Ma, Jie Wu, Min Zheng, Rui Yang, Xiu Li, Xuefeng Xiao, Yansong Tang","submitted_at":"2022-03-21T08:08:15Z","abstract_excerpt":"The vanilla self-attention mechanism inherently relies on pre-defined and steadfast computational dimensions. Such inflexibility restricts it from possessing context-oriented generalization that can bring more contextual cues and global representations. To mitigate this issue, we propose a Scalable Self-Attention (SSA) mechanism that leverages two scaling factors to release dimensions of query, key, and value matrices while unbinding them with the input. This scalability fetches context-oriented generalization and enhances object sensitivity, which pushes the whole network into a more effectiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10790","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2203.10790/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2203.10790","created_at":"2026-07-05T04:40:52.605257+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.10790v2","created_at":"2026-07-05T04:40:52.605257+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10790","created_at":"2026-07-05T04:40:52.605257+00:00"},{"alias_kind":"pith_short_12","alias_value":"JAUYE53JHJSJ","created_at":"2026-07-05T04:40:52.605257+00:00"},{"alias_kind":"pith_short_16","alias_value":"JAUYE53JHJSJLGIU","created_at":"2026-07-05T04:40:52.605257+00:00"},{"alias_kind":"pith_short_8","alias_value":"JAUYE53J","created_at":"2026-07-05T04:40:52.605257+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JAUYE53JHJSJLGIUGBSNH2JXCF","json":"https://pith.science/pith/JAUYE53JHJSJLGIUGBSNH2JXCF.json","graph_json":"https://pith.science/api/pith-number/JAUYE53JHJSJLGIUGBSNH2JXCF/graph.json","events_json":"https://pith.science/api/pith-number/JAUYE53JHJSJLGIUGBSNH2JXCF/events.json","paper":"https://pith.science/paper/JAUYE53J"},"agent_actions":{"view_html":"https://pith.science/pith/JAUYE53JHJSJLGIUGBSNH2JXCF","download_json":"https://pith.science/pith/JAUYE53JHJSJLGIUGBSNH2JXCF.json","view_paper":"https://pith.science/paper/JAUYE53J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.10790&json=true","fetch_graph":"https://pith.science/api/pith-number/JAUYE53JHJSJLGIUGBSNH2JXCF/graph.json","fetch_events":"https://pith.science/api/pith-number/JAUYE53JHJSJLGIUGBSNH2JXCF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JAUYE53JHJSJLGIUGBSNH2JXCF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JAUYE53JHJSJLGIUGBSNH2JXCF/action/storage_attestation","attest_author":"https://pith.science/pith/JAUYE53JHJSJLGIUGBSNH2JXCF/action/author_attestation","sign_citation":"https://pith.science/pith/JAUYE53JHJSJLGIUGBSNH2JXCF/action/citation_signature","submit_replication":"https://pith.science/pith/JAUYE53JHJSJLGIUGBSNH2JXCF/action/replication_record"}},"created_at":"2026-07-05T04:40:52.605257+00:00","updated_at":"2026-07-05T04:40:52.605257+00:00"}